2025
Efficient Extreme Large-Scale Speaker Verification: Dynamic Active Sub Fully-Connected Layers for Faster Training and Memory Optimization
ICASSP 2025accepted
Using larger scale datasets in the training stage of speaker verification model usually leads to better performance. However, when the speaker number of the training dataset becomes extreme large (e.g., more than 1 million), the training speed and GPU memory demand will become bottlenecks which are…